INDEX

Explanations

patterns and structures in data strings or code

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MemoryWarning

-0.54

marvin

-0.50

 defStyle

-0.48

 encantó

-0.48

tuce

-0.46

featureID

-0.46

Greater

-0.45

WebVitals

-0.45

setSuccess

-0.45

 consectetur

-0.44

POSITIVE LOGITS

setVerticalGroup

0.65

 Exacts

0.63

 CreateTagHelper

0.63

SharedDtor

0.60

 propOrder

0.57

WriteTagHelper

0.56

consulté

0.55

----</

0.55

 ModelExpression

0.53

JPL

0.53

Activations Density 0.058%

patterns and structures in data strings or code

No Comments

No Known Activations